AI agents call list_all_tools to retrieve information from Model Context Shell without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available tools on the server without modifying or executing anything. It is a read-only discovery mechanism similar to 'list' or 'get' operations. Even though the description is empty, the name unambiguously indicates a passive enumeration function.
From the tool's definition Tool name 'list_all_tools' indicates enumeration/querying of available tools with no side effects. Description is empty but naming convention strongly suggests listing/discovery functionality.
Documented attack patterns abuse exactly the kind of access list_all_tools gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Model Context Shell, and nothing reaches the server without passing your rules. This is the rule we recommend for list_all_tools:
{
"version": "1",
"default": "deny",
"tools": {
"list_all_tools": {}
}
}list_all_tools is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list_all_tools. It is categorised as a Read tool in the Model Context Shell MCP Server, which means it retrieves data without modifying state.
Register the Model Context Shell MCP server in PolicyLayer and add a rule for list_all_tools: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Model Context Shell. Nothing to install.
list_all_tools is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_all_tools rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_all_tools. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_all_tools is provided by the Model Context Shell MCP server (stackloklabs/model-context-shell). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Model Context Shell, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Model Context Shell tools catalogued and risk-classified — across an index of 43,000+ MCP servers.